nicknisi/skills

Latest recorded source activity: October 21, 2026 at 14:34

SkillsMP catalog refreshed: November 12, 2026 at 12:52

skills collected: 19

GitHub stars: 5
GitHub forks: 0

Install with an AI assistant

Copy this prompt into the AI assistant you're using.

Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/nicknisi/skills.

Repository README

Repository README source: docs/README.md

Read the source README

Expand full README

# Skills A collection of [pi](https://pi.dev) and Claude Code skills — drop-in expertise modules that shape how an agent handles specific kinds of requests. Each skill is a self-contained directory with a `SKILL.md` file that defines its trigger conditions, workflow, and constraints. ## What is a skill? A skill is a markdown file that tells the agent: - **When to activate** — trigger phrases, user intent patterns, or request types - **What to do** — the workflow, steps, or process to follow - **What not to do** — boundaries, anti-patterns, or things to refuse - **How to output** — format, style, or quality standards Skills live in the agent's context and are selected automatically based on the user's request. They are not plugins or code — they are structured prompts that govern behavior. ## Skill catalog | Skill | Description | |-------|-------------| | **brainrot** | Turn any topic, doc, or wall of text into "sludge content": a phone-shaped (9:16) page with a narrated ELI5 lesson (neural TTS via OpenAI or ElevenLabs with word-synced captions, browser voice fallback) on top and Minecraft-style 3D parkour underneath, synced to the lesson (new biome per beat, a stunt on each beat's key phrase). One click exports the whole lesson as a 1080×1920 MP4 for posting. Triggered by "brainrot," "sludge," "subway surfers," "I can't focus on this," "read this to me." | | **content-machine** | Turn Nick Nisi's raw material into a blog post draft in his voice. Use when the user says "write a blog post," "draft a post," "write about [topic]," "turn my notes into a blog post," or provides scattered ideas that need shaping. Produces a deliberately flat draft with sourced facts and tagged gaps — never a finished post. | | **diagnosing-bugs** | Diagnosis loop for hard bugs and performance regressions. Systematic root-cause analysis when something is broken, throwing, failing, or slow. | | **domain-modeling** | Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a `CONTEXT.md`, or recording an ADR. | | **eli5** | Explain a topic to a complete novice using an HTML artifact with big pictures and few words. Triggered by "eli5" or "explain like I'm 5." | | **explain-this** | Explain any digital artifact — paper, PDF, article, or codebase — so the person actually understands it, not just skims. Uses comprehension quizzes and spaced repetition. | | **grill** | Grill the user relentlessly about a plan, decision, or idea. Stress-test thinking by surfacing hidden assumptions and arguing for the simplest version. | | **llms-visibility** | Make websites, docs, blogs, or landing pages visible and readable to LLMs and AI agents. Covers `llms.txt`, Markdown content negotiation, `Link` headers, and `Content-Signal` in `robots.txt`. | | **research** | Investigate a question against high-trust primary sources and capture findings as a Markdown file in the repo. Delegated to background agents when legwork is needed. | | **scandinavian-design** | Apply a refined Scandinavian visual system with a neutral black-and-white foundation, restrained sans-serif typography, purposeful product imagery, generous spacing, and clear page choreography. | | **show-me** | Help the user understand the current topic visually with concise diagrams, code-shape sketches, and focused HTML artifacts. | | **triage** | Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs. | | **unslop** | Cut AI tells from any writing. Scans prose for statistically overrepresented AI writing patterns and rewrites flagged sections. | | **wayfinder** | Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on the issue tracker, and resolve them one at a time until the way to the destination is clear. | | **wizard** | Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, or walking an unfamiliar third-party dashboard. | ## Structure ``` skills/ ├── <skill-name>/ │ └── SKILL.md # Required. The skill definition. │ └── (other files) # Optional. Scripts, references, templates. ``` Each `SKILL.md` follows this convention: ```markdown --- name: <short-name> description: '<one-line description including trigger conditions>' --- # <Title> ## Workflow ### 1. <Step name> <Instructions> ## Anti-patterns: do NOT implement - **<Pattern>** — <Why to refuse it> ## Tradeoffs to confirm before shipping - **<Decision>** — <What to ask the user> ``` ## Usage These skills are designed for [pi](https://pi.dev), a coding agent harness that supports skill-based context injection. To use them: 1. Clone or symlink this repo into your pi skills directory 2. Reference skills by name in your pi configuration 3. The agent will automatically select the appropriate skill based on your request Some skills are also compatible with Claude Code's skill system. ## Adding a skill 1. Create a directory with a descriptive name 2. Write a `SKILL.md` with clear frontmatter and structured instructions 3. Test it with real requests before committing 4. Keep it focused — one skill, one responsibility ## Attribution Some skills are original; others are adapted from public skill repositories: - **llms-visibility** — adapted from [evilmartians/agent-skills](https://github.com/evilmartians/agent-skills) When adapting a skill, attribution is preserved in the skill file itself.

Loading the repository README…

Skills in this repository

Project Management Specialists Software Developers Graphic Designers Postsecondary Teachers, All Other

8 occupation categories · 84% classified

skill

occupation

description

updated

merge-risk

unclassified

Use when assessing the risk of merging a PR

2026-10-21

brag

unclassified

Turn the current project website into a short, polished, shareable launch video using Hyperframes. Use when someone says "/brag", "let's brag about this", "make a launch video", "turn this into a video", or wants to share what they built. Reads the project…

2026-09-24

diagnosing-bugs

Software Quality Assurance Analysts & Testers

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

2026-09-17

orc

Software Developers

Orchestrate complex work from kickoff or mid-task. Preserve progress, bring in useful help, choose models by the work and how reliably it can be verified, and own the integrated result. Use when asked to orchestrate, parallelize, bring in agents, or change an…

2026-09-17

triage

Project Management Specialists

Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.

2026-09-17

prove-it-works

Software Quality Assurance Analysts & Testers

Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the actual value, inspect the diff), not a proxy, self-report, or 'it compiles.'

2026-09-17

reflect

Software Developers

Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill. Use when the user says reflect.

2026-09-17

ai-news

Graphic Designers

Fetch and curate AI news from X/Twitter list into a whimsical, animated HTML artifact. Use when user asks for AI news, AI digest, what's happening in AI, or wants a summary of AI announcements, papers, and releases.

2026-09-17

brainrot

Graphic Designers

Turn any topic, doc, article, README, or wall of text into "sludge content": a split-screen web page with a narrated ELI5-style lesson on the left (browser text-to-speech, one-word-at-a-time TikTok captions) and an endless pixel platformer or…

2026-09-17

content-machine

Technical Writers

Turn Nick Nisi's raw material into content drafts in his voice — blog posts and conference talks, primarily. Use when the user says "write a post," "draft a talk," "write about [topic]," "turn my notes into writing," or provides scattered ideas that need…

2026-09-17

eli5

Postsecondary Teachers, All Other

Explain a topic to a complete novice using an HTML artifact with big pictures and few words. Use when the user says "eli5", "explain like I'm 5", or asks for a beginner-friendly visual explanation of any topic.

2026-09-17

explain-this

Postsecondary Teachers, All Other

Explain any digital artifact — a paper, PDF, article, or codebase — so the person actually understands it, not just skims it. Explanations are shaped by a persistent learner profile, gated by comprehension quizzes, and feed a spaced-repetition review loop.…

2026-09-17

grilling

Project Management Specialists

Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

2026-09-17

llms-visibility

Software Developers

Make websites, docs, blogs, or landing pages visible and readable to LLMs and AI agents — ChatGPT, Claude, Perplexity, Cursor, Claude Code, and other coding agents that fetch URLs. Use this for any request involving llms.txt, llms-full.txt, serving…

2026-09-17

research

Market Research Analysts & Marketing Specialists

Explicitly requested research workflow that delegates primary-source investigation to a background agent and saves a Markdown report. Use only when the user explicitly invokes this skill or requests this delegated research workflow.

2026-09-17

show-me

unclassified

Help the user understand the current topic visually with concise diagrams, code-shape sketches, and focused HTML artifacts.

2026-09-17

unslop

Technical Writers

Edit writing to remove AI patterns and improve its voice. Use only when the user explicitly invokes this skill or requests an Unslop editing pass.

2026-09-17

wayfinder

Project Management Specialists

Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.

2026-09-17

wizard

Network & Computer Systems Administrators

Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover.…

2026-09-17

Showing 19 of 19 collected skills.